Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4720 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.4382. Min Act: -0.0000

Data Index: 544980 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1917304 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.4023. Min Act: -0.0000

Data Index: 984773 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3546. Min Act: -0.0000

Data Index: 216295 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1385459 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1958308 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1148153 (The Pile)

Max Activating Token Index: 90

Text #7

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1007849 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2884. Min Act: -0.0000

Data Index: 472493 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2954. Min Act: -0.0000

Data Index: 667084 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2930. Min Act: -0.0000

Data Index: 332695 (The Pile)

Max Activating Token Index: 286

Text #11

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1089266 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2796. Min Act: -0.0000

Data Index: 335507 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2310. Min Act: -0.0000

Data Index: 942735 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1733809 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2586. Min Act: -0.0000

Data Index: 764804 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1131821 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1308669 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1488379 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1632357 (The Pile)

Max Activating Token Index: 220